blockrun

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

BlockRun

BlockRun works with Claude Code and Google Antigravity.

You can't generate images. You have no real-time X/Twitter access. BlockRun gives you these capabilities.

BlockRun 可与 Claude Code 和 Google Antigravity 配合使用。

你无法生成图像，也无法获取实时X/Twitter数据，BlockRun可为你提供这些功能。

Philosophy

设计理念

You have a wallet. When you need a capability you lack, you pay for it autonomously.

You Need	You Call	Pricing
Image generation	DALL-E	$0.04/image
Real-time X data	Grok + Live Search	$0.025/source
Second opinion	GPT-5.2	$1.75/M input, $14/M output
Cheaper processing	DeepSeek	$0.14/M input, $0.28/M output

How it works: BlockRun uses x402 micropayments to route your requests to OpenAI, xAI, Google, and other providers. No API keys needed - your wallet pays per token.

你拥有一个钱包，当你需要自身不具备的功能时，可以自主付费使用。

你需要的功能	调用的工具	定价
图像生成	DALL-E	$0.04/张
实时X数据	Grok + 实时搜索	$0.025/数据源
二次意见	GPT-5.2	输入$1.75/百万token，输出$14/百万token
低成本处理	DeepSeek	输入$0.14/百万token，输出$0.28/百万token

工作原理： BlockRun 使用x402微支付将你的请求路由到OpenAI、xAI、Google等服务商。无需API密钥，你的钱包按token计费。

Budget Control (Optional)

预算控制（可选）

If the user specifies a budget (e.g., "use at most $1"), track spending and stop when budget is reached:

python

from blockrun_llm import setup_agent_wallet

client = setup_agent_wallet()
budget = 1.0  # User's budget

如果用户指定了预算（例如“最多使用1美元”），请跟踪支出，达到预算后停止调用：

python

from blockrun_llm import setup_agent_wallet

client = setup_agent_wallet()
budget = 1.0  # 用户设定的预算

Before each call, check if within budget

每次调用前检查是否在预算内

spending = client.get_spending() if spending['total_usd'] >= budget: print(f"Budget reached: ${spending['total_usd']:.4f} spent") # Stop making calls else: response = client.chat("openai/gpt-5.2", "Hello!")

spending = client.get_spending() if spending['total_usd'] >= budget: print(f"已达预算：已花费${spending['total_usd']:.4f}") # 停止调用 else: response = client.chat("openai/gpt-5.2", "Hello!")

At the end, report spending

最后报告支出情况

spending = client.get_spending() print(f"💰 Total spent: ${spending['total_usd']:.4f} across {spending['calls']} calls")

undefined

spending = client.get_spending() print(f"💰 总支出：${spending['total_usd']:.4f}，共调用{spending['calls']}次")

undefined

When to Use

使用场景

Trigger	Your Action
User explicitly requests ("blockrun second opinion with GPT on...", "use grok to check...", "generate image with dall-e")	Execute via BlockRun
User needs something you can't do (images, live X data)	Suggest BlockRun, wait for confirmation
You can handle the task fine	Do it yourself, don't mention BlockRun

触发条件	你的操作
用户明确请求（如“blockrun用GPT给出二次意见...”、“用grok查询...”、“用dall-e生成图像”）	通过BlockRun执行
用户需要你无法完成的任务（图像生成、实时X数据）	建议使用BlockRun，等待用户确认
你可以独立完成任务	自行处理，无需提及BlockRun

Example User Prompts

用户提示示例

Users will say things like:

User Says	What You Do
"blockrun generate an image of a sunset"	Call DALL-E via ImageClient
"use grok to check what's trending on X"	Call Grok with `search=True`
"blockrun GPT review this code"	Call GPT-5.2 via LLMClient
"what's the latest news about AI agents?"	Suggest Grok (you lack real-time data)
"generate a logo for my startup"	Suggest DALL-E (you can't generate images)
"blockrun check my balance"	Show wallet balance via `get_balance()`
"blockrun deepseek summarize this file"	Call DeepSeek for cost savings

用户可能会这样说：

用户提问	你的操作
"blockrun生成一张日落的图片"	通过ImageClient调用DALL-E
"用grok查看X上的热门内容"	调用Grok并设置 `search=True`
"blockrun用GPT审核这段代码"	通过LLMClient调用GPT-5.2
"关于AI Agent的最新消息是什么？"	建议使用Grok（你没有实时数据）
"为我的创业公司生成一个logo"	建议使用DALL-E（你无法生成图像）
"blockrun查看我的余额"	通过 `get_balance()` 显示钱包余额
"blockrun用deepseek总结这个文件"	调用DeepSeek以节省成本

Wallet & Balance

钱包与余额

Use

setup_agent_wallet()

to auto-create a wallet and get a client. This shows the QR code and welcome message on first use.

Initialize client (always start with this):

python

from blockrun_llm import setup_agent_wallet

client = setup_agent_wallet()  # Auto-creates wallet, shows QR if new

Check balance (when user asks "show balance", "check wallet", etc.):

python

balance = client.get_balance()  # On-chain USDC balance
print(f"Balance: ${balance:.2f} USDC")
print(f"Wallet: {client.get_wallet_address()}")

Show QR code for funding:

python

from blockrun_llm import generate_wallet_qr_ascii, get_wallet_address

使用

setup_agent_wallet()

自动创建钱包并获取客户端。首次使用时会显示二维码和欢迎信息。

初始化客户端（务必从这一步开始）：

python

from blockrun_llm import setup_agent_wallet

client = setup_agent_wallet()  # 自动创建钱包，若为新钱包则显示二维码

查询余额（当用户询问“显示余额”、“检查钱包”等）：

python

balance = client.get_balance()  # 链上USDC余额
print(f"余额：${balance:.2f} USDC")
print(f"钱包地址：{client.get_wallet_address()}")

显示充值二维码：

python

from blockrun_llm import generate_wallet_qr_ascii, get_wallet_address

ASCII QR for terminal display

终端显示ASCII格式的二维码

print(generate_wallet_qr_ascii(get_wallet_address()))

undefined

print(generate_wallet_qr_ascii(get_wallet_address()))

undefined

SDK Usage

SDK使用方法

Prerequisite: Install the SDK with

pip install blockrun-llm

前置条件： 使用

pip install blockrun-llm

安装SDK

Basic Chat

基础对话

python

from blockrun_llm import setup_agent_wallet

client = setup_agent_wallet()  # Auto-creates wallet if needed
response = client.chat("openai/gpt-5.2", "What is 2+2?")
print(response)

python

from blockrun_llm import setup_agent_wallet

client = setup_agent_wallet()  # 若需要则自动创建钱包
response = client.chat("openai/gpt-5.2", "2+2等于多少？")
print(response)

Check spending

查询支出

spending = client.get_spending() print(f"Spent ${spending['total_usd']:.4f}")

undefined

spending = client.get_spending() print(f"已花费${spending['total_usd']:.4f}")

undefined

Real-time X/Twitter Search (xAI Live Search)

实时X/Twitter搜索（xAI实时数据API）

IMPORTANT: For real-time X/Twitter data, you MUST enable Live Search with

search=True

search_parameters

python

from blockrun_llm import setup_agent_wallet

client = setup_agent_wallet()

重要提示： 要获取实时X/Twitter数据，必须通过

search=True

或

search_parameters

启用实时搜索。

python

from blockrun_llm import setup_agent_wallet

client = setup_agent_wallet()

Simple: Enable live search with search=True

简单用法：设置search=True启用实时搜索

response = client.chat( "xai/grok-3", "What are the latest posts from @blockrunai on X?", search=True # Enables real-time X/Twitter search ) print(response)

undefined

response = client.chat( "xai/grok-3", "X上@blockrunai的最新帖子是什么？", search=True # 启用实时X/Twitter搜索 ) print(response)

undefined

Advanced X Search with Filters

带筛选条件的高级X搜索

python

from blockrun_llm import setup_agent_wallet

client = setup_agent_wallet()

response = client.chat(
    "xai/grok-3",
    "Analyze @blockrunai's recent content and engagement",
    search_parameters={
        "mode": "on",
        "sources": [
            {
                "type": "x",
                "included_x_handles": ["blockrunai"],
                "post_favorite_count": 5
            }
        ],
        "max_search_results": 20,
        "return_citations": True
    }
)
print(response)

python

from blockrun_llm import setup_agent_wallet

client = setup_agent_wallet()

response = client.chat(
    "xai/grok-3",
    "分析@blockrunai近期的内容和互动情况",
    search_parameters={
        "mode": "on",
        "sources": [
            {
                "type": "x",
                "included_x_handles": ["blockrunai"],
                "post_favorite_count": 5
            }
        ],
        "max_search_results": 20,
        "return_citations": True
    }
)
print(response)

Image Generation

图像生成

python

from blockrun_llm import ImageClient

client = ImageClient()
result = client.generate("A cute cat wearing a space helmet")
print(result.data[0].url)

python

from blockrun_llm import ImageClient

client = ImageClient()
result = client.generate("一只戴着太空头盔的可爱猫咪")
print(result.data[0].url)

xAI Live Search Reference

xAI实时搜索参考

Live Search is xAI's real-time data API. Cost: $0.025 per source (default 10 sources = ~$0.26).

To reduce costs, set

max_search_results

to a lower value:

python

undefined

实时搜索是xAI的实时数据API，定价为每个数据源$0.025（默认10个数据源≈$0.26）。

如需降低成本，可将

max_search_results

设置为更小的值：

python

undefined

Only use 5 sources (~$0.13)

仅使用5个数据源（≈$0.13）

response = client.chat("xai/grok-3", "What's trending?", search_parameters={"mode": "on", "max_search_results": 5})

undefined

response = client.chat("xai/grok-3", "当前热门内容是什么？", search_parameters={"mode": "on", "max_search_results": 5})

undefined

Search Parameters

搜索参数

Parameter	Type	Default	Description
`mode`	string	"auto"	"off", "auto", or "on"
`sources`	array	web,news,x	Data sources to query
`return_citations`	bool	true	Include source URLs
`from_date`	string	-	Start date (YYYY-MM-DD)
`to_date`	string	-	End date (YYYY-MM-DD)
`max_search_results`	int	10	Max sources to return (customize to control cost)

参数	类型	默认值	说明
`mode`	字符串	"auto"	可选值："off"、"auto"、"on"
`sources`	数组	web,news,x	要查询的数据源
`return_citations`	布尔值	true	是否包含源URL
`from_date`	字符串	-	开始日期（格式：YYYY-MM-DD）
`to_date`	字符串	-	结束日期（格式：YYYY-MM-DD）
`max_search_results`	整数	10	返回的最大数据源数量（可自定义以控制成本）

Source Types

数据源类型

X/Twitter Source:

python

{
    "type": "x",
    "included_x_handles": ["handle1", "handle2"],  # Max 10
    "excluded_x_handles": ["spam_account"],        # Max 10
    "post_favorite_count": 100,  # Min likes threshold
    "post_view_count": 1000      # Min views threshold
}

Web Source:

python

{
    "type": "web",
    "country": "US",  # ISO alpha-2 code
    "allowed_websites": ["example.com"],  # Max 5
    "safe_search": True
}

News Source:

python

{
    "type": "news",
    "country": "US",
    "excluded_websites": ["tabloid.com"]  # Max 5
}

X/Twitter数据源：

python

{
    "type": "x",
    "included_x_handles": ["handle1", "handle2"],  # 最多10个
    "excluded_x_handles": ["spam_account"],        # 最多10个
    "post_favorite_count": 100,  # 最低点赞数阈值
    "post_view_count": 1000      # 最低浏览量阈值
}

网页数据源：

python

{
    "type": "web",
    "country": "US",  # ISO alpha-2国家代码
    "allowed_websites": ["example.com"],  # 最多5个
    "safe_search": True
}

新闻数据源：

python

{
    "type": "news",
    "country": "US",
    "excluded_websites": ["tabloid.com"]  # 最多5个
}

Available Models

可用模型

Model	Best For	Pricing
`openai/gpt-5.2`	Second opinions, code review, general	$1.75/M in, $14/M out
`openai/gpt-5-mini`	Cost-optimized reasoning	$0.30/M in, $1.20/M out
`openai/o4-mini`	Latest efficient reasoning	$1.10/M in, $4.40/M out
`openai/o3`	Advanced reasoning, complex problems	$10/M in, $40/M out
`xai/grok-3`	Real-time X/Twitter data	$3/M + $0.025/source
`deepseek/deepseek-chat`	Simple tasks, bulk processing	$0.14/M in, $0.28/M out
`google/gemini-2.5-flash`	Very long documents, fast	$0.15/M in, $0.60/M out
`openai/dall-e-3`	Photorealistic images	$0.04/image
`google/nano-banana`	Fast, artistic images	$0.01/image

M = million tokens. Actual cost depends on your prompt and response length.

模型	适用场景	定价
`openai/gpt-5.2`	二次意见、代码审核、通用场景	输入$1.75/百万token，输出$14/百万token
`openai/gpt-5-mini`	成本优化型推理	输入$0.30/百万token，输出$1.20/百万token
`openai/o4-mini`	最新高效推理模型	输入$1.10/百万token，输出$4.40/百万token
`openai/o3`	高级推理、复杂问题	输入$10/百万token，输出$40/百万token
`xai/grok-3`	实时X/Twitter数据	$3/百万token + $0.025/数据源
`deepseek/deepseek-chat`	简单任务、批量处理	输入$0.14/百万token，输出$0.28/百万token
`google/gemini-2.5-flash`	超长文档处理、快速响应	输入$0.15/百万token，输出$0.60/百万token
`openai/dall-e-3`	写实风格图像生成	$0.04/张
`google/nano-banana`	快速生成艺术风格图像	$0.01/张

M = 百万token。实际成本取决于你的提示词和响应长度。

Cost Reference

成本参考

All LLM costs are per million tokens (M = 1,000,000 tokens).

Model	Input	Output
GPT-5.2	$1.75/M	$14.00/M
GPT-5-mini	$0.30/M	$1.20/M
Grok-3 (no search)	$3.00/M	$15.00/M
DeepSeek	$0.14/M	$0.28/M

Fixed Cost Actions
Grok Live Search	$0.025/source (default 10 = $0.25)
DALL-E image	$0.04/image
Nano Banana image	$0.01/image

Typical costs: A 500-word prompt (~750 tokens) to GPT-5.2 costs ~$0.001 input. A 1000-word response (~1500 tokens) costs ~$0.02 output.

所有大模型成本以百万token为单位（M = 1,000,000 token）。

模型	输入成本	输出成本
GPT-5.2	$1.75/M	$14.00/M
GPT-5-mini	$0.30/M	$1.20/M
Grok-3（无搜索）	$3.00/M	$15.00/M
DeepSeek	$0.14/M	$0.28/M

固定成本操作	定价
Grok实时搜索	$0.025/数据源（默认10个=$0.25）
DALL-E图像生成	$0.04/张
Nano Banana图像生成	$0.01/张

典型成本： 给GPT-5.2发送500词提示词（约750token），输入成本约$0.001；1000词响应（约1500token），输出成本约$0.02。

Setup & Funding

设置与充值

Wallet location:

$HOME/.blockrun/.session

(e.g.,

/Users/username/.blockrun/.session

)

First-time setup:

Wallet auto-creates when
```
setup_agent_wallet()
```
is called
Check wallet and balance:

python

from blockrun_llm import setup_agent_wallet
client = setup_agent_wallet()
print(f"Wallet: {client.get_wallet_address()}")
print(f"Balance: ${client.get_balance():.2f} USDC")

Fund wallet with $1-5 USDC on Base network

Show QR code for funding (ASCII for terminal):

python

from blockrun_llm import generate_wallet_qr_ascii, get_wallet_address
print(generate_wallet_qr_ascii(get_wallet_address()))

钱包位置：

$HOME/.blockrun/.session

（例如

/Users/username/.blockrun/.session

）

首次设置：

调用
```
setup_agent_wallet()
```
时自动创建钱包
查看钱包和余额：

python

from blockrun_llm import setup_agent_wallet
client = setup_agent_wallet()
print(f"钱包地址：{client.get_wallet_address()}")
print(f"余额：${client.get_balance():.2f} USDC")

在Base网络给钱包充值1-5 USDC

显示充值二维码（终端显示ASCII格式）：

python

from blockrun_llm import generate_wallet_qr_ascii, get_wallet_address
print(generate_wallet_qr_ascii(get_wallet_address()))

Troubleshooting

故障排除

"Grok says it has no real-time access" → You forgot to enable Live Search. Add

search=True

python

response = client.chat("xai/grok-3", "What's trending?", search=True)

Module not found → Install the SDK:

pip install blockrun-llm

“Grok提示无实时访问权限” → 你忘记启用实时搜索，添加

search=True

：

python

response = client.chat("xai/grok-3", "当前热门内容是什么？", search=True)

“模块未找到” → 安装SDK：

pip install blockrun-llm

Updates

更新SDK

bash

pip install --upgrade blockrun-llm

bash

pip install --upgrade blockrun-llm